Unsupervised Deep Features for Privacy Image Classification

TL;DR

This paper introduces a novel unsupervised deep feature extraction method tailored for privacy image classification, effectively handling limited data and producing compact, discriminative features that outperform existing approaches.

Contribution

The paper proposes an unsupervised deep feature extraction technique using K-means clustering and feature fusion, suitable for limited privacy image datasets.

Findings

Outperforms state-of-the-art deep features in accuracy

Reduces feature size and improves testing efficiency

Effective on limited data scenarios

Abstract

Sharing images online poses security threats to a wide range of users due to the unawareness of privacy information. Deep features have been demonstrated to be a powerful representation for images. However, deep features usually suffer from the issues of a large size and requiring a huge amount of data for fine-tuning. In contrast to normal images (e.g., scene images), privacy images are often limited because of sensitive information. In this paper, we propose a novel approach that can work on limited data and generate deep features of smaller size. For training images, we first extract the initial deep features from the pre-trained model and then employ the K-means clustering algorithm to learn the centroids of these initial deep features. We use the learned centroids from training features to extract the final features for each testing image and encode our final features with the triangle encoding. To improve the discriminability of the features, we further perform the fusion of two proposed unsupervised deep features obtained from different layers. Experimental results show that the proposed features outperform state-of-the-art deep features, in terms of both classification accuracy and testing time.